Gemma2B-StaproCoder
This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2988
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.733 | 0.05 | 100 | 0.5294 |
| 0.5149 | 0.1 | 200 | 0.4275 |
| 0.2925 | 0.15 | 300 | 0.3854 |
| 0.3588 | 0.2 | 400 | 0.3794 |
| 0.3145 | 0.25 | 500 | 0.3766 |
| 0.4036 | 0.3 | 600 | 0.3728 |
| 0.4822 | 0.35 | 700 | 0.3553 |
| 0.3456 | 0.4 | 800 | 0.3428 |
| 0.3978 | 0.45 | 900 | 0.3367 |
| 0.2692 | 0.5 | 1000 | 0.3365 |
| 0.4038 | 0.55 | 1100 | 0.3203 |
| 0.3345 | 0.6 | 1200 | 0.3210 |
| 0.2668 | 0.65 | 1300 | 0.3130 |
| 0.2617 | 0.7 | 1400 | 0.3103 |
| 0.2657 | 0.75 | 1500 | 0.3099 |
| 0.2633 | 0.8 | 1600 | 0.3041 |
| 0.4033 | 0.85 | 1700 | 0.3045 |
| 0.2208 | 0.9 | 1800 | 0.3017 |
| 0.2646 | 0.95 | 1900 | 0.2989 |
| 0.3054 | 1.0 | 2000 | 0.2988 |
Framework versions
- PEFT 0.9.0
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 5
Model tree for rreit/Gemma2B-StaproCoder
Base model
google/gemma-2b